AI-NeuralNet-Mesh
view release on metacpan or search on metacpan
$self->{random} = $rand;
}
# Sets/gets column width for printing lists in debug modes 1,3, and 4.
sub col_width {
my $self = shift;
my $width = shift;
return $self->{col_width} if(!$width);
$self->{col_width} = $width;
}
# Sets/gets run const. facter in the network. Setting a value of 0
# disables run const. factor.
sub const {
my $self = shift;
my $const = shift;
return $self->{const} if(!(defined $const));
$self->{const} = $const;
}
# Return benchmark time from last learn() operation.
sub benchmark {
shift->{benchmarked};
}
# Same as benchmark()
sub benchmarked {
benchmark(shift);
}
# Return the last error in the mesh, or undef if no error.
sub error {
my $self = shift;
return undef if !$self->{error};
chomp($self->{error});
return $self->{error}."\n";
}
# Used to format array ref into columns
# Usage:
# join_cols(\@array,$row_length_in_elements,$high_state_character,$low_state_character);
# Can also be called as method of your neural net.
# If $high_state_character is null, prints actual numerical values of each element.
sub join_cols {
no strict 'refs';
shift if(substr($_[0],0,4) eq 'AI::');
my $map = shift;
my $break = shift;
my $a = shift;
my $b = shift;
my $x;
foreach my $el (@{$map}) {
my $str = ((int($el))?$a:$b);
$str=$el."\0" if(!$a);
print $str; $x++;
if($x>$break-1) { print "\n"; $x=0; }
}
print "\n";
}
# Returns percentage difference between all elements of two
# array refs of exact same length (in elements).
# Now calculates actual difference in numerical value.
sub pdiff {
no strict 'refs';
shift if(substr($_[0],0,4) eq 'AI::');
my $a1 = shift;
my $a2 = shift;
my $a1s = $#{$a1};
my $a2s = $#{$a2};
my ($a,$b,$diff,$t);
$diff=0;
for my $x (0..$a1s) {
$a = $a1->[$x]; $b = $a2->[$x];
if($a!=$b) {
if($a<$b){$t=$a;$a=$b;$b=$t;}
$a=1 if(!$a); $diff+=(($a-$b)/$a)*100;
}
}
$a1s = 1 if(!$a1s);
return sprintf("%.10f",($diff/$a1s));
}
# Returns $fa as a percentage of $fb
sub p {
shift if(substr($_[0],0,4) eq 'AI::');
my ($fa,$fb)=(shift,shift);
sprintf("%.3f",$fa/$fb*100); #((($fb-$fa)*((($fb-$fa)<0)?-1:1))/$fa)*100
}
# Returns the index of the element in array REF passed with the highest
# comparative value
sub high {
shift if(substr($_[0],0,4) eq 'AI::');
my $ref1 = shift; my ($el,$len,$tmp); $tmp=0;
foreach $el (@{$ref1}) { $len++ }
for my $x (0..$len-1) { $tmp = $x if($ref1->[$x] > $ref1->[$tmp]) }
return $tmp;
}
# Returns the index of the element in array REF passed with the lowest
# comparative value
sub low {
shift if(substr($_[0],0,4) eq 'AI::');
my $ref1 = shift; my ($el,$len,$tmp); $tmp=0;
foreach $el (@{$ref1}) { $len++ }
for my $x (0..$len-1) { $tmp = $x if($ref1->[$x] < $ref1->[$tmp]) }
return $tmp;
}
# Following is a collection of a few nifty custom activation functions.
# range() is exported by default, the rest you can get with:
# use AI::NeuralNet::Mesh ':acts'
# The ':all' tag also gets these into your namespace.
#
# range() returns a closure limiting the output
# of that node to a specified set of values.
# Good for output layers.
#
# usage example:
# $net->activation(4,range(0..5));
# or:
# ..
# {
# nodes => 1,
# activation => range 5..2
# }
# ..
# You can also pass an array containing the range
# values (not array ref), or you can pass a comma-
# seperated list of values as parameters:
#
# $net->activation(4,range(@numbers));
# $net->activation(4,range(6,15,26,106,28,3));
#
# Note: when using a range() activatior, train the
# net TWICE on the data set, because the first time
# the range() function searches for the top value in
# the inputs, and therefore, results could flucuate.
# The second learning cycle guarantees more accuracy.
#
sub range {
my @r=@_;
hidden layers.
Each hash refrence is expected to have AT LEAST the "nodes" key set to the number
of nodes (neurons) in that layer. The other two keys are optional. If "activation" is left
out, it defaults to "linear". If "threshold" is left out, it defaults to 0.50.
The "activation" key can be one of four values:
linear ( simply use sum of inputs as output )
sigmoid [ sigmoid_1 ] ( only positive sigmoid )
sigmoid_2 ( positive / 0 /negative sigmoid )
\&code_ref;
"sigmoid_1" is an alias for "sigmoid".
The code ref option allows you to have a custom activation function for that layer.
The code ref is called with this syntax:
$output = &$code_ref($sum_of_inputs, $self);
The code ref is expected to return a value to be used as the output of the node.
The code ref also has access to all the data of that node through the second argument,
a blessed hash refrence to that node.
See CUSTOM ACTIVATION FUNCTIONS for information on several included activation functions
other than the ones listed above.
Three of the activation syntaxes are shown in the first constructor above, the "linear",
"sigmoid" and code ref types.
You can also set the activation and threshold values after network creation with the
activation() and threshold() methods.
=item $net->learn($input_map_ref, $desired_result_ref [, options ]);
NOTE: learn_set() now has increment-degrading turned OFF by default. See note
on the degrade flag, below.
This will 'teach' a network to associate an new input map with a desired
result. It will return a string containg benchmarking information.
You can also specify strings as inputs and ouputs to learn, and they will be
crunched automatically. Example:
$net->learn('corn', 'cob');
Note, the old method of calling crunch on the values still works just as well.
The first two arguments may be array refs (or now, strings), and they may be
of different lengths.
Options should be written on hash form. There are three options:
inc => $learning_gradient
max => $maximum_iterations
error => $maximum_allowable_percentage_of_error
degrade => $degrade_increment_flag
$learning_gradient is an optional value used to adjust the weights of the internal
connections. If $learning_gradient is ommitted, it defaults to 0.002.
$maximum_iterations is the maximum numbers of iteration the loop should do.
It defaults to 1024. Set it to 0 if you never want the loop to quit before
the pattern is perfectly learned.
$maximum_allowable_percentage_of_error is the maximum allowable error to have. If
this is set, then learn() will return when the perecentage difference between the
actual results and desired results falls below $maximum_allowable_percentage_of_error.
If you do not include 'error', or $maximum_allowable_percentage_of_error is set to -1,
then learn() will not return until it gets an exact match for the desired result OR it
reaches $maximum_iterations.
$degrade_increment_flag is a simple flag used to allow/dissalow increment degrading
during learning based on a product of the error difference with several other factors.
$degrade_increment_flag is off by default. Setting $degrade_increment_flag to a true
value turns increment degrading on.
In previous module releases $degrade_increment_flag was not used, as increment degrading
was always on. In this release I have looked at several other network types as well
as several texts and decided that it would be better to not use increment degrading. The
option is still there for those that feel the inclination to use it. I have found some areas
that do need the degrade flag to work at a faster speed. See test.pl for an example. If
the degrade flag wasn't in test.pl, it would take a very long time to learn.
=item $net->learn_set(\@set, [ options ]);
This takes the same options as learn() (learn_set() uses learn() internally)
and allows you to specify a set to learn, rather than individual patterns.
A dataset is an array refrence with at least two elements in the array,
each element being another array refrence (or now, a scalar string). For
each pattern to learn, you must specify an input array ref, and an ouput
array ref as the next element. Example:
my @set = (
# inputs outputs
[ 1,2,3,4 ], [ 1,3,5,6 ],
[ 0,2,5,6 ], [ 0,2,1,2 ]
);
Inputs and outputs in the dataset can also be strings.
See the paragraph on measuring forgetfulness, below. There are
two learn_set()-specific option tags available:
flag => $flag
pattern => $row
If "flag" is set to some TRUE value, as in "flag => 1" in the hash of options, or if the option "flag"
is not set, then it will return a percentage represting the amount of forgetfullness. Otherwise,
learn_set() will return an integer specifying the amount of forgetfulness when all the patterns
are learned.
If "pattern" is set, then learn_set() will use that pattern in the data set to measure forgetfulness by.
If "pattern" is omitted, it defaults to the first pattern in the set. Example:
my @set = (
[ 0,1,0,1 ], [ 0 ],
[ 0,0,1,0 ], [ 1 ],
[ 1,1,0,1 ], [ 2 ], # <---
[ 0,1,1,0 ], [ 3 ]
);
If you wish to measure forgetfulness as indicated by the line with the arrow, then you would
pass 2 as the "pattern" option, as in "pattern => 2".
Now why the heck would anyone want to measure forgetfulness, you ask? Maybe you wonder how I
even measure that. Well, it is not a vital value that you have to know. I just put in a
"forgetfulness measure" one day because I thought it would be neat to know.
How the module measures forgetfulness is this: First, it learns all the patterns
in the set provided, then it will run the very first pattern (or whatever pattern
is specified by the "row" option) in the set after it has finished learning. It
will compare the run() output with the desired output as specified in the dataset.
In a perfect world, the two should match exactly. What we measure is how much that
they don't match, thus the amount of forgetfulness the network has.
Example (from examples/ex_dow.pl):
# Data from 1989 (as far as I know..this is taken from example data on BrainMaker)
my @data = (
# Mo CPI CPI-1 CPI-3 Oil Oil-1 Oil-3 Dow Dow-1 Dow-3 Dow Ave (output)
[ 1, 229, 220, 146, 20.0, 21.9, 19.5, 2645, 2652, 2597], [ 2647 ],
[ 2, 235, 226, 155, 19.8, 20.0, 18.3, 2633, 2645, 2585], [ 2637 ],
[ 3, 244, 235, 164, 19.6, 19.8, 18.1, 2627, 2633, 2579], [ 2630 ],
[ 4, 261, 244, 181, 19.6, 19.6, 18.1, 2611, 2627, 2563], [ 2620 ],
[ 5, 276, 261, 196, 19.5, 19.6, 18.0, 2630, 2611, 2582], [ 2638 ],
[ 6, 287, 276, 207, 19.5, 19.5, 18.0, 2637, 2630, 2589], [ 2635 ],
[ 7, 296, 287, 212, 19.3, 19.5, 17.8, 2640, 2637, 2592], [ 2641 ]
);
# Learn the set
my $f = $net->learn_set(\@data,
inc => 0.1,
max => 500,
);
# Print it
print "Forgetfullness: $f%";
This is a snippet from the example script examples/finance.pl, which demonstrates DOW average
prediction for the next month. A more simple set defenition would be as such:
my @data = (
[ 0,1 ], [ 1 ],
[ 1,0 ], [ 0 ]
);
$net->learn_set(\@data);
=item $net->join_cols($array_ref,$row_length_in_elements,$high_state_character,$low_state_character);
This is more of a utility function than any real necessary function of the package.
Instead of joining all the elements of the array together in one long string, like join() ,
it prints the elements of $array_ref to STDIO, adding a newline (\n) after every $row_length_in_elements
number of elements has passed. Additionally, if you include a $high_state_character and a $low_state_character,
it will print the $high_state_character (can be more than one character) for every element that
has a true value, and the $low_state_character for every element that has a false value.
If you do not supply a $high_state_character, or the $high_state_character is a null or empty or
undefined string, it join_cols() will just print the numerical value of each element seperated
by a null character (\0). join_cols() defaults to the latter behaviour.
=item $net->extend(\@array_of_hashes);
This allows you to re-apply any activations and thresholds with the same array ref which
you created a network with. This is useful for re-applying code ref activations after a load()
call without having to type the code ref twice.
You can also specify the extension in a simple array ref like this:
$net->extend([2,3,1]);
Which will simply add more nodes if needed to set the number of nodes in each layer to their
respective elements. This works just like the respective new() constructor, above.
NOTE: Your net will probably require re-training after adding nodes.
=item $net->extend_layer($layer,\%hash);
With this you can modify only one layer with its specifications in a hash refrence. This hash
refrence uses the same keys as for the last new() constructor form, above.
You can also specify just the number of nodes for the layer in this form:
$net->extend_layer(0,5);
Which will set the number of nodes in layer 0 to 5 nodes. This is the same as calling:
$net->add_nodes(0,5);
Which does the exact same thing. See add_nodes() below.
NOTE: Your net will probably require re-training after adding nodes.
=item $net->add_nodes($layer,$total_nodes);
This method was created mainly to service the extend*() group of functions, but it
can also be called independently. This will add nodes as needed to layer C<$layer> to
make the nodes in layer equal to $total_nodes.
NOTE: Your net will probably require re-training after adding nodes.
=item $net->p($a,$b);
Returns a floating point number which represents $a as a percentage of $b.
=item $net->intr($float);
Rounds a floating-point number rounded to an integer using sprintf() and int() , Provides
better rounding than just calling int() on the float. Also used very heavily internally.
=item $net->high($array_ref);
Returns the index of the element in array REF passed with the highest comparative value.
=item $net->low($array_ref);
Returns the index of the element in array REF passed with the lowest comparative value.
=item $net->pdiff($array_ref_A, $array_ref_B);
This function is used VERY heavily internally to calculate the difference in percent
between elements of the two array refs passed. It returns a %.20f (sprintf-format)
percent sting.
=item $net->show();
This will dump a simple listing of all the weights of all the connections of every neuron
in the network to STDIO.
=item $net->crunch($string);
This splits a string passed with /[\s\t]/ into an array ref containing unique indexes
to the words. The words are stored in an intenal array and preserved across load() and save()
calls. This is designed to be used to generate unique maps sutible for passing to learn() and
run() directly. It returns an array ref.
The words are not duplicated internally. For example:
$net->crunch("How are you?");
Will probably return an array ref containing 1,2,3. A subsequent call of:
$net->crunch("How is Jane?");
Will probably return an array ref containing 1,4,5. Notice, the first element stayed
the same. That is because it already stored the word "How". So, each word is stored
only once internally and the returned array ref reflects that.
=item $net->uncrunch($array_ref);
Uncrunches a map (array ref) into an scalar string of words seperated by ' ' and returns the
string. This is ment to be used as a counterpart to the crunch() method, above, possibly to
uncrunch() the output of a run() call. Consider the below code (also in ./examples/ex1.pl):
use AI::NeuralNet::Mesh;
my $net = AI::NeuralNet::Mesh->new(2,3);
for (0..3) {
$net->learn_set([
$net->crunch("I love chips."), $net->crunch("That's Junk Food!")),
$net->crunch("I love apples."), $net->crunch("Good, Healthy Food.")),
$net->crunch("I love pop."), $net->crunch("That's Junk Food!")),
$net->crunch("I love oranges."),$net->crunch("Good, Healthy Food."))
]);
}
print $net->run_uc("I love corn.")),"\n";
On my system, this responds with, "Good, Healthy Food." If you try to run crunch() with
"I love pop.", though, you will probably get "Food! apples. apples." (At least it returns
that on my system.) As you can see, the associations are not yet perfect, but it can make
for some interesting demos!
( run in 1.223 second using v1.01-cache-2.11-cpan-39bf76dae61 )